Read Heraldo de Aragon on your iPad or Kindle in no time. Click download to load the free ebook on your reader.

Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.

Download for free »

Daily newspaper from Aragon

Language: es

Requires Subscription: No, it's available as free ebook

Schedule Every morning

			  #!/usr/bin/env  python
__license__     = 'GPL v3'
__copyright__   = '04 December 2010, desUBIKado'
__author__      = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon'
__version__     = 'v0.04'
__date__        = '6, Januery 2011'
'''
[url]http://www.heraldo.es/[/url]
'''

import time
import re
from calibre.web.feeds.news import BasicNewsRecipe

class heraldo(BasicNewsRecipe):
    __author__     = 'desUBIKado'
    description    = 'Daily newspaper from Aragon'
    title          = u'Heraldo de Aragon'
    publisher      = 'OJD Nielsen'
    category       = 'News, politics, culture, economy, general interest'
    language       = 'es'
    timefmt        = '[%a, %d %b, %Y]'
    oldest_article = 2
    delay          = 1
    max_articles_per_feed = 100
    use_embedded_content  = False
    remove_javascript = True
    no_stylesheets = True


    feeds          = [
                        (u'Portadas', u'http://www.heraldo.es/index.php/mod.portadas/mem.rss')
                     ]



    keep_only_tags     = [dict(name='div', attrs={'id':['dts','com']})]

    remove_tags        = [dict(name='a', attrs={'class':['com flo-r','enl-if','enl-df']}),
                          dict(name='div', attrs={'class':['brb-b-s con marg-btt','cnt-rel con']}),
                          dict(name='form', attrs={'class':'form'}),
                          dict(name='ul', attrs={'id':['cont-tags','pag-1']})]

    remove_tags_before = dict(name='div' , attrs={'id':'dts'})
    remove_tags_after  = dict(name='div' , attrs={'id':'com'})

    def get_cover_url(self):
       cover = None
       st = time.localtime()
       year = str(st.tm_year)
       month = "%.2d" % st.tm_mon
       day = "%.2d" % st.tm_mday
		#[url]http://oldorigin-www.heraldo.es/20101211/primeras/portada_aragon.pdf[/url]
       cover='http://oldorigin-www.heraldo.es/'+ year +  month + day +'/primeras/portada_aragon.pdf'
       br = BasicNewsRecipe.get_browser()
       try:
           br.open(cover)
       except:
           self.log("\nPortada no disponible")
           cover ='http://www.heraldo.es/MODULOS/global/publico/interfaces/img/logo-Heraldo.png'
       return cover


    extra_css = '''
                    .con strong{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:16px;}
                    .con h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:30px;}
                    .con span{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:12px;}
                    .ent {font-family:Arial,Helvetica,sans-serif; font-weight:normal; font-style:italic; font-size:18px;}
                    img{margin-bottom: 0.4em}
                '''

    preprocess_regexps = [

# To separate the comments with a blank line
                           (re.compile(r'<div id="com"', re.DOTALL|re.IGNORECASE), lambda match: '<br><div id="com"')
                         ]